Skip to main content
affpapa.org
RU EN
skill CX Codex

critique — Claude Code skill: multi-judge review of finished work

The critique skill runs finished work past several AI judges: they review it independently, debate their findings, and agree on a shared list of issues.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add NeoLabHQ/context-engineering-kit --skill critique -a claude-code
Open on GitHub

What critique does

The critique skill reviews work you have already completed. A coordinator gathers the context — the original request, changed files, decisions made along the way — and spawns three judges in parallel through the Task tool. One checks alignment with the requirements, one weighs the chosen approach against alternatives, one looks at code quality and refactoring spots.

Each judge works alone first, then asks itself verification questions and revises its verdict based on the answers. After that the judges debate their findings and settle on agreed recommendations. The whole thing is report-only: the skill changes nothing, it hands the findings to you.

Pass no arguments and it falls back to the conversation history and recent file changes; if the scope is fuzzy it asks what to review. Runs in Claude, Codex, Cursor, GitHub Copilot, Gemini CLI and OpenCode.

What it helps with

  • check whether every part of the original request was actually done
  • surface places where the approach could have gone another way
  • get a list of code issues without touching the code
  • separate missed requirements from scope creep
  • collect a second opinion on a fresh change before committing

Example prompts for the agent

  • Run critique on the changes in src/auth/session.ts
  • Critique the last commit and show what's still open from the task
  • Run critique over all the work in this conversation

How to install critique

1Skills CLI (Vercel)

npx skills add NeoLabHQ/context-engineering-kit --skill critique -a claude-code

2Manually: put the files in place

~/.claude/skills/critique/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/critique/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about critique

How do I install critique in Claude?

Run npx skills add NeoLabHQ/context-engineering-kit --skill critique -a claude-code. The skill file then lands at ~/.claude/skills/critique/SKILL.md.

What does critique do?

It puts finished work through three independent judges: a requirements check, an approach review and a code quality pass. The judges debate and return one combined report of findings.

Does critique fix the code itself?

No. It reads and reports only, leaving the findings for you. You apply the fixes yourself or hand them to the agent as a separate task.

Similar skills

Everything for Code review and refactoring →
pre-publish-review code-yeongyu Orchestrates a 12-agent release gate for npm packages. Detects unpublished diffs and reviews breaking changes before you push to the registry. CX Codex +1 753installs opencode-ensemble hueyexe A skill that tells the lead agent how to split work into independent slices, hand them to teammates and merge the results. Useful when a task has parallel branches. CX Codex +1 681installs deep-audit pedrohcgs Splits a theory, proof, paper or codebase into components, fans out independent skeptics and fixes every confirmed defect. Built for when one review pass is not enough. CX Codex +1 ★ 1,668repo stars agent-teams Seth Hobson Runs several Claude agents at once for parallel code review, hypothesis-driven debugging and coordinated feature work. CX Codex ★ 41,729repo stars gem-team official mubaidr gem-team gives AI coding tasks a workflow with planning, TDD, and verification. Use it when you want to resume larger tasks from a saved plan. ★ 40,418repo stars design-critique Owl-Listener The skill runs a team design critique: session framing, feedback rules, and action items with owners. Built for sessions with people in the room. CX Codex +1 2,200installs

From the same set55

subagent-driven-development Runs an implementation plan through fresh subagents and puts code review between tasks, so context stays clean and issues surface early. CX Codex +1 1,300installs judge-with-debate The skill runs three independent judges who argue over a solution's score until they agree. Useful when a single pass feels too thin for a real verdict. CX Codex +1 1,300installs update-docs Updates project documentation based on uncommitted git changes or the latest commit. Keeps README files, docs/, and JSDoc comments synchronized with your codebase. CX Codex +1 1,300installs root-cause-tracing A skill that walks the agent backward through the call stack until it finds the original trigger, then fixes there instead of at the crash site. CX Codex +1 1,300installs brainstorm Turns rough project ideas into detailed specifications through guided dialogue. It compares six architectural options before any code or implementation planning begins. CX Codex +1 1,300installs multi-agent-patterns A skill that lays out three ways to split work across subagents: supervisor, peer-to-peer and hierarchical. Useful once one agent runs out of context. CX Codex +1 1,300installs write-concisely This skill enforces classic style rules from William Strunk Jr.'s 1918 guide across human-facing docs. It strips filler words and switches passive phrasing into active voice. CX Codex +1 1,300installs setup-codemap-cli Configures the Codemap CLI utility to inspect project file trees and module dependencies. Helpful when giving an AI agent clear architectural context across Git branches. CX Codex +1 1,200installs

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor